JPH0764480A - Voice recognition device for on-vehicle processing information - Google Patents

Abstract

PURPOSE:To perform voice recognition of an input language through voice efficiently and quickly and reduce the possibility of erroneous recognition due to a similar language by deciding the group of voice dictionary using at recognizing the input language based on the distance against the present position of a vehicle in preferred order. CONSTITUTION:When an operator says a destination or a passing place through a microphone, the place name is recognized by a voice recognition part 3, and the coordinate data and the letter code of the position of the recognized place name are read out from a table. In order to efficiently recognize the input language through voice in the voice recognition part 3, the names of places and facilities registered in a voice dictionary 2 are divided into the territories of existence. Under control by a voice dictionary access control part 4, a preferred order is provided on the groups of the voice dictionary using at recognizing the input language, based on the distance against the present position of a vehicle required by a navigation device 5.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an in-vehicle information processing device such as an in-vehicle navigation device for displaying the current position of a vehicle on a map displayed on a screen, and particularly to an input given by voice to the in-vehicle information processing device. The present invention relates to a vehicle-mounted information processing voice recognition device that recognizes a vocabulary of instructions.

[0002]

2. Description of the Related Art Recently, by accumulatively calculating a position on a two-dimensional coordinate while detecting a traveling distance and a traveling direction of a vehicle by self-contained inertial navigation, or G
A vehicle-mounted navigation device that measures the position by radio navigation such as PS (Global Positioning System), obtains the current position of the vehicle on the map, and displays the current position of the vehicle on the map displayed on the screen. In this case, by inputting the names of each of the starting point, the passing point and the destination by voice in advance, each of the starting point, the passing point and the destination is displayed at a predetermined position on the map and the planned travel route is displayed. A device that can be set has been developed (see Japanese Patent Application Laid-Open No. 3-21817).

However, in such a case, for example,
When you input "Kobe" by voice in the destination setting mode, the data of the input word by that voice and the reference data of the vocabulary registered in the voice dictionary in advance are compared and collated, and the matching degree of both data is used. After recognizing the input word, the position of Kobe recognized by the voice is obtained from the table, the map information of the area including Kobe is read from the map information storage medium, and the map is displayed on the screen.
The destination is automatically set at the position of Kobe on the map.

At this time, a place name, a facility name, etc. are input by voice, and the voice recognition is performed, so that a predetermined map can be searched or the position of the facility on the map can be searched. In this case, it is necessary to increase the vocabulary such as place names and facility names registered in the voice dictionary in order to make it more detailed.

[0005]

The problem to be solved is to use a voice dictionary in which a large number of vocabularies such as place names and facility names are registered, and compare the input words by voice to compare the input words. If voice recognition is performed, it takes time for the comparison and collation.

Further, when the vocabulary such as place names and facility names registered in the voice dictionary becomes large, the number of similar words also increases, and the recognition error tends to increase.

[0007]

According to the present invention, even if the vocabulary such as a place name or a facility name related to the display contents of a navigation map registered in a voice dictionary becomes large, voice recognition of an input word by voice is performed. In order to make it possible to perform efficiently, the registered contents of the voice dictionary are divided into groups according to regions, and when recognizing input words based on the distance to the current position of the vehicle required by the navigation device. The groups of voice dictionaries to be used are decided in order of priority.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In a vehicle-mounted navigation voice recognition device according to the present invention, as shown in FIG. 1, a microphone 1 into which voice is input, and vocabulary relating to the display contents of a navigation map, such as a place name or a facility name, are used. Voice dictionary 2 in which reference data of each digitized vocabulary such as, for example, is grouped and registered in advance for each region, and an input signal by voice from the microphone 1 is converted into digital information, and the digitized input is performed. A vehicle provided from a voice recognition unit 3 that recognizes an input word by comparing and collating word information with reference information of a vocabulary registered in the voice dictionary 2 and observing the degree of coincidence of both data, and a navigation device 5. Of the current position signal P of the voice dictionary and based on the distance to the current position, the group of the voice dictionary used when recognizing the input word is prioritized. It is made from the voice dictionary access control unit 4 that determined with.

The voice dictionary 2 includes grammar rules and the like.
A vocabulary such as a place name or a facility name is decomposed into a unit sound string, and digitized reference information based on the decomposed unit sound string is registered.

Then, in the voice dictionary 2, as shown in FIG. 2, coordinate data values of latitude and longitude of a position where the place or facility exists corresponding to a registered word such as a place name or facility name. Is set in the table together with the character code of the registered word.

The voice recognition unit 3 decomposes the voice signal input from the microphone 1 into unit sound strings, digitizes the signals of the decomposed unit sound strings, and creates a voice dictionary 2 that matches the information. Recognize input words by selecting registered reference information. A known method is applied as a method for recognizing the input word in the voice recognition unit 3.

As the navigation device 5, well-known navigation devices using self-contained inertial navigation or radio navigation are widely applied, but here, a device for measuring the position by radio navigation by GPS is used. ing.

The navigation device 5 finds out the current position of the vehicle on the map from the GPS position measuring unit 51 and the measured position, and reproduces it from the map information storage medium 52 such as a CD-ROM 53. A predetermined map is displayed on the screen of the display 54 on the basis of the map information read through, and a signal processing unit 55 including a microcomputer for displaying the current position of the vehicle on the map and an operator for the signal processing unit 55. The input operation section 56 is capable of giving an input command by the, and the speaker 57 for giving the operator an audio instruction from the signal processing section 55.

With the above-mentioned configuration, under the control of the program set in the signal processing unit 55, the map information in the area where the current position of the own vehicle exists is read from the map information storage medium 52. The map is displayed, and the map is displayed on the screen of the display 54, and the current position of the vehicle is displayed as a mark at a predetermined position on the map.

Then, when the navigation device 5 enters an input mode such as setting a planned traveling route in response to an input command from the input operation unit 56, the signal processing unit 55 causes the speaker 57 to indicate "destination destination" by voice synthesis. Please ",
The instruction “Please tell me the passing point on the way” is issued one after another.

Then, in response to the instruction, when the operator says the place name of the destination or the passing point (or the name of the target facility) from the microphone 1, the place name (or the facility name) is recognized by the voice recognition unit 3. The coordinate data of the recognized position of the place name (or the position where the facility or the like exists) and the character code are read from the table and given to the signal processing unit 55.

As a result, under the control of the signal processing unit 55, the map is searched from the coordinate data of the position of the destination or the passing point, and the map information of the area where the position exists is stored in the map information storage medium 52. The map is read and displayed on the screen of the display 54, and a mark of a destination or a passing point is displayed at a predetermined position on the map. Then, the place name (or facility name, etc.) input by voice is auxiliary displayed in the corner on the screen.

In such a case, particularly in the present invention, the place name or the facility name registered in the voice dictionary 2 is provided so that the voice recognition unit 3 can efficiently recognize the input word by voice. When the input word is recognized based on the distance to the current position of the vehicle, which is obtained by the navigation device 5, under the control of the voice dictionary access control unit 4 after grouping such as according to the area in which they exist. The groups of the voice dictionary 2 used for are given priority.

Further, according to the present invention, each group of the voice dictionary 2 is arranged so that the map search can be performed more efficiently and appropriately according to the situation of short distance movement or long distance movement of the vehicle when the navigation device 5 is used. The hierarchy is divided into a plurality of stages according to the level of detail of the display contents of the map, and priority is given to a higher level hierarchy with a low level of detail within each group. Then, the hierarchy having the lowest priority among the groups having the lowest priority is excluded from the target of the voice recognition.

Usually, when the navigation device 5 is used, when a vehicle is moved for a short distance such as a commercial vehicle, it is necessary to search a map with a detailed place name such as a municipality name or a ward number level. When moving a vehicle over a long distance, such as a trip, it is necessary to search a map by place name at the level of prefecture or municipality level.

Specifically, as shown in FIG. 3, for example,
In the map of Japan, the name of a place in the whole country or the name of a facility scattered throughout the country is divided into four areas, Hokkaido (A), Honshu (B), Shikoku (C), and Kyushu (D), according to the area where it exists.
Divide into two groups. And, for example, (A),
The groups (B), (C), and (D) are placed in the upper levels A1, B1, and C1 of the prefecture level, the middle levels A2, B2, and C2 of the municipal level, and the lower level of the ward number level. Hierarchical layers A3, B3, and C3 are respectively hierarchized and divided into nine blocks in total.

Then, the voice dictionary access control section 4 follows the procedure set in advance for the group and each group based on the distance to the current position of the vehicle on the map which is obtained by the navigation device 5. Hierarchical selection and priority are decided as follows.

Look for a group of regions in which the vehicle's current location is located. At that time, for example, it is assumed that the group (B) is searched.

For groups (A), (C) and (D) in areas where the current position of the vehicle does not exist, the shortest distance from the current position to the area of each group is calculated.

At this time, for example, the position data of the center of the area of each group is registered in the internal memory of the voice dictionary access control unit 4 as known data, and the position data of the vehicle on the map obtained by the navigation device 5 is obtained. A straight line distance between the current position and the position of the center of the area of each group is calculated by a predetermined calculation process.

The groups (A), (C), and (D) in areas where the current position of the vehicle does not exist are arranged in the ascending order of the calculated distances. At that time, for example, (C) → (A) →
It is assumed that they are arranged in the order of (D).

Lower layers A3 and C in groups (A), (C) and (D) in areas where the current position of the vehicle does not exist
3 and D3 are considered to have no possibility and are excluded from the target of voice recognition.

The priority order from the upper hierarchy in the group (B) where the current position of the vehicle exists is B1 → B.
Determined as 2 → B3.

Next, the groups (C) → (A) → (D) arranged in the order of distance where the current position of the vehicle does not exist are prioritized, and further the priorities are given from the upper hierarchy in each group. , C1 → C2 → A1 → A2 → D1 →
Determine as D2.

Finally, as a priority order for accessing the voice dictionary 2, B1 → B2 → B3 → C1 → C2 → A1 →
A2 → D1 → D2 is obtained.

In this way, if the priority order for accessing the voice dictionary 2 is obtained based on the current position of the vehicle,
The voice dictionary access control unit 4 first executes the voice recognition process of the input word by using the block B1 having the highest priority in the voice dictionary 2, and when it fails, the next priority is given until the input word is recognized. Blocks B2, B3 ...
Is used to execute the voice recognition process.

Therefore, according to the present invention, the voice dictionary 2
Even if a lot of vocabulary such as place name and facility name is registered in
When searching for a map used for navigation, with the block of the priority determined as the one that is likely to recognize the place name or facility name input by voice in relation to the current position of the vehicle at that time. Since the voice dictionary 2 is accessed, useless comparison and collation work can be eliminated, and voice recognition of an input word can be efficiently and promptly performed.

Further, according to the present invention, since the voice dictionary 2 is accessed for each block to perform voice recognition of the input word, the probability of erroneous recognition due to similar words is reduced, and accurate voice recognition is performed. You will be able to do it.

Further, in the present invention, a means for storing the specific position information and a means for reading the stored specific position information are provided, and when the specific position information is read, Specific position information is given to the voice dictionary access control unit 4, and selection and prioritization of groups of the voice dictionary 2 used when recognizing an input word based on the distance to the specific position and layers in each group. The ranking is decided in the same manner as described above.

Specifically, under the control of the signal processing unit 55 in the navigation device 5, the position of a home or a company, a predetermined destination and the purpose thereof are input by an input operation from the input operation unit 56 or by voice input. Specific position information such as a passing point on the way to the ground can be registered in the internal memory of the signal processing unit 55.

Then, for example, when a predetermined destination is instructed to be input from the input operation unit 56, or when a predetermined destination is input by voice, the position information of the destination is read and The read position information is given to the voice dictionary access control unit 4.

When the specific position information is given, the voice dictionary access control unit 4 uses the distance to the specific position instead of the current position of the vehicle as described above, and the group and each of them in the voice dictionary 2. The selection and priority of the layers in the group are determined in the same manner as described above.

However, if the selection and priority of the groups in the voice dictionary 2 and the layers in each group are determined based on the distance to the specific position, for example, a predetermined destination is selected. When the map search is performed by using the place name or the facility name in the vicinity, the voice recognition can be quickly performed.

[0039]

As described above, in the voice recognition device for vehicle-mounted navigation according to the present invention, the input word by voice and the voice dictionary are accessed, and the place name and the facility related to the display content of the navigation map registered in it are accessed. When recognizing input words by comparing and collating vocabulary such as names, the registered contents of the voice dictionary are divided into groups according to regions and input based on the distance to the current position of the vehicle required by the navigation device. After deciding the group of the voice dictionary to be used when recognizing words with priority,
The priority group enables partial access to the voice dictionary, which enables efficient and speedy voice recognition of input words by voice, and effectively reduces the probability of false recognition by similar words. It has the advantage that

[Brief description of drawings]

FIG. 1 is a block diagram showing an embodiment of a vehicle-mounted navigation voice recognition device according to the present invention.

FIG. 2 is a table showing an example of table contents of a voice dictionary.

FIG. 3 is a table showing an example in which place names, facility names, etc. in a navigation map are divided into blocks according to regions, and each block is hierarchized.

[Explanation of symbols]

 1 Microphone 2 Voice Dictionary 3 Voice Recognition Unit 4 Voice Dictionary Access Control Unit 5 Navigation Device 51 Position Measuring Unit 52 Map Information Storage Medium 53 Playback Device 54 Display 55 Signal Processing Unit 56 Input Operation Unit 57 Speaker

Claims (4)

[Claims] 1. Data of an input word by voice and reference data of a vocabulary related to operation contents of an in-vehicle information processing device such as display contents of a navigation map registered in a voice dictionary are compared and collated. An in-vehicle information processing voice recognition device for recognizing an input word by observing the degree of coincidence of data, a voice dictionary in which registered contents are grouped according to regions, and a navigation device for obtaining the current position of a vehicle on a map, A vehicle-mounted vehicle characterized by using a voice dictionary access control means for deciding a group of voice dictionaries to be used for recognizing an input word based on a distance to a current position obtained by the navigation device, in order of priority. Speech recognition device for information processing. 2. The voice dictionary groups are hierarchized into a plurality of levels according to the level of detail of the display contents of the navigation map, and the higher level of hierarchy is given priority. A voice recognition device for in-vehicle information processing according to the above item 1. 3. The in-vehicle information processing voice recognition device according to claim 2, wherein a hierarchy having a lower priority is excluded from the targets of voice recognition. 4. A means for storing specific position information and a means for reading the stored specific position information are provided, and when the specific position information is read, the specific position information is a voice dictionary. The item of the above-mentioned item 1, characterized in that the group of the voice dictionary used when recognizing an input word is given to the access control means based on the distance to the specific position in order of priority. Voice recognition device for in-vehicle information processing.